He Zheng

The quantitative assessment of forest fire severity is significant for understanding the changes in ecological processes caused by fire disturbances. As a novel spectral index derived from the multi-objective optimization algorithm, the Analytic Burned Area Index (ABAI) was originally designed for mapping burned areas. However, the performance of the ABAI in detecting forest fire severity has not been addressed. To fill this gap, this study utilizes a ground-based dataset of fire severity (the composite burn index, CBI) to validate the effectiveness of the ABAI in detecting fire severity. First, the effectiveness of the ABAI regarding forest fire severity was validated using uni-temporal images from Sentinel-2 and Landsat 8 OLI. Second, fire severity accuracy derived from the ABAI with bi-temporal images from both sensors was evaluated. Finally, the performance of the ABAI was tested with different sensors and compared with representative spectral indices. The results show that (1) the ABAI demonstrates significant advantages in terms of accuracy and stability in assessing fire severity, particularly in areas with large numbers of terrain shadows and severe burn regions; (2) the ABAI also shows great advantages in assessing regional forest fire severity when using only uni-temporal remotely sensed data, and it performed almost as well as the dNBR in bi-temporal images. (3) The ABAI outperforms commonly used indices with both Sentinel-2 and Landsat 8 data, indicating that the ABAI is normally more generalizable and powerful and provides an optional spectral index for fire severity evaluation.

Forest fires cause environmental and economic damage, destroy large areas of land and displace entire communities. Accurate extraction of fire-affected areas is of vital importance to support post-fire management strategies and account for the environmental impact of fires. In this paper, an analytical burned area index, called ABAI, was proposed to map burned areas from the newly launched Sentinel-2 images. The innovation of this method is to separate the fire scars from other typical land covers by formulating different objective functions, which involved three main components: First, spectral differences between the burned land and other land covers were characterized by analyzing the spectral features of the existing burned area indices. Then, for each type of land cover, we formed an objective function by linear combination of bands with the values of band ratios. Second, all the objective functions and possible constraints were formulated as a multi-objective optimization problem, and then it was solved using a linear programming approach. Finally, the ABAI spectral index was achieved with the optimizing coefficients derived from the multi-objective problem. To validate the effectiveness of the proposed spectral index, three experimental datasets, clipped from Sentinel-2 images at different places, were tested and compared with baseline indices, such as normalized burned area (NBR) and burned area index (BAI) methods. Experimental results demonstrated that the injection of a green band to the spectral index has led to good applicability in burned area detection, where the ABAI can avoid most of the confusion presented by shadows or shallow water. Compared to other burned area indices, the proposed ABAI achieved the best classification accuracy, with the overall accuracy being over 90%. Visually, our approach significantly outperforms other spectral indexed methods, especially in confused areas covered by water bodies and shadows.

In various applications of airborne laser scanning (ALS), the classification of the point cloud is a basic and key step. It requires assigning category labels to each point, such as ground, building or vegetation. Convolutional neural networks have achieved great success in image classification and semantic segmentation, but they cannot be directly applied to point cloud classification because of the disordered and unstructured characteristics of point clouds. In this paper, we design a novel convolution operator to extract local features directly from unstructured points. Based on this convolution operator, we define the convolution layer, construct a convolution neural network to learn multi-level features from the point cloud, and obtain the category label of each point in an end-to-end manner. The proposed method is evaluated on two ALS datasets: the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen 3D Labeling benchmark and the 2019 IEEE Geoscience and Remote Sensing Society (GRSS) Data Fusion Contest (DFC) 3D dataset. The results show that our method achieves state-of-the-art performance for ALS point cloud classification, especially for the larger dataset DFC: we get an overall accuracy of 97.74% and a mean intersection over union (mIoU) of 0.9202, ranking in first place on the contest website.